© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15115
    Prev
    Next
    INDEX
    Explanations

    references to specific technology products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and brand names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    被称为
    -0.46
     popular
    -0.46
    zbęd
    -0.43
    向着
    -0.41
    组成
    -0.41
     denominado
    -0.41
     denominada
    -0.41
     constituyen
    -0.40
     populer
    -0.40
     funkcjon
    -0.40
    POSITIVE LOGITS
     stuff
    1.03
     thingy
    0.94
     vids
    0.84
    UserScript
    0.78
     regs
    0.77
     iirc
    0.76
    +#+#
    0.75
     thing
    0.73
     guy
    0.70
    SpringBootTest
    0.70
    Activations Density 1.014%

    No Known Activations